Databricks GenAI Associate Exam Flashcards

Q: What topics do these Databricks GenAI flashcards cover?

They cover RAG architecture, Vector Search, chunking and embeddings, prompt engineering, model serving and selection, MLflow and LLMOps, agents and tool calling, Agent Bricks and MCP, evaluation and RAG metrics, online monitoring and AI Gateway, governance and security, and AI Functions with structured output.

Q: Are these flashcards copied from exam questions?

No. The cards are original study prompts written to reinforce concepts, distinctions, and platform-specific tradeoffs. They are not reproductions of live exam questions or of the practice question bank.

Q: How should I use these flashcards with the practice questions?

Use the flashcards for active recall of concepts and distinctions, then use the practice questions to apply those concepts in scenarios. Revisit any topic where you miss a practice question or cannot explain the tradeoff in your own words.

Q: How many cards are in this deck and how are they organized?

The deck has 50 cards grouped under 12 stable topic labels that mirror the official six-domain blueprint: Design Applications, Data Preparation, Application Development, Assembling and Deploying Apps, Governance, and Evaluation and Monitoring.

Q: Does this deck reflect the March 18, 2026 blueprint changes?

Yes. Cards on Agent Bricks, managed MCP endpoints, AI Gateway usage tracking, custom scorers, and agent monitoring are included so candidates testing on or after March 18, 2026 cover the updated objectives.

Question 1

RAG vs fine-tuning for proprietary knowledge

Accepted Answer

RAG retrieves fresh documents at query time, so it beats fine-tuning when the knowledge is proprietary, frequently changing, or must be cited. Fine-tuning is better for shaping style, tone, or stable behavior, but it cannot efficiently encode weekly policy updates and does not give you source attribution.

Question 2

When hardcoded prompts fail

Accepted Answer

Hardcoding answers into a system prompt works only for tiny, static knowledge. As soon as the source documents change or the question space grows, the prompt becomes unmaintainable and answers go stale. RAG scales because the knowledge lives outside the model and is fetched on demand.

Question 3

RAG vs agentic workflow decision

Accepted Answer

Use plain RAG when one retrieval pass answers the question. Choose an agent when the task needs multiple steps, tool calls, conditional branching, or iterative retrieval. Agents add flexibility but also add latency, cost, and harder evaluation, so do not graduate to one unless single-pass retrieval genuinely cannot solve the problem.

Question 4

Problem decomposition for GenAI pipelines

Accepted Answer

Break a GenAI request into explicit stages such as retrieval, context assembly, generation, and post-processing so each can be measured and fixed independently. Monolithic prompts hide where quality is lost, which makes debugging slow. Explicit stages give you clear failure boundaries and let you swap components without rebuilding the whole app.

Question 5

Context augmentation in RAG

Accepted Answer

Context augmentation inserts retrieved chunks into the prompt so the model conditions its answer on supplied evidence instead of parametric memory. The consequence is that answer quality is bounded by retrieval quality: if the wrong chunks are retrieved, even a strong model will produce a wrong or unsupported answer.

Question 6

Delta Sync vs Direct Vector Access index

Accepted Answer

Delta Sync indexes automatically follow a Delta table and refresh as the table changes, so they are the default when the source is Delta. Direct Vector Access indexes skip the sync and require you to manage vectors and metadata yourself, which only makes sense when the embeddings come from outside Databricks or the source is not a Delta table.

Question 7

Change Data Feed for Delta Sync indexes

Accepted Answer

A standard Delta Sync index reads the source Delta table's change stream to apply incremental updates. If Change Data Feed is not enabled on the table, index creation fails because there is no supported way to track row changes. Enable CDF on the source table before creating the index.

Question 8

Vector Search endpoint

Accepted Answer

A Vector Search endpoint is the compute resource that hosts one or more indexes and serves similarity queries. It is separate from the index itself, so you can host multiple indexes on one endpoint and size the endpoint independently from the data. Endpoint sizing affects latency and cost, not correctness.

Question 9

Embedding vector column in a Vector Search index

Accepted Answer

The index needs a column that holds the embedding vector for each row. For Delta Sync indexes Databricks can compute the embedding for you from a text column; for Direct Vector Access indexes you must supply the precomputed vector column. Mismatched dimensions between the embedding column and the query vector cause queries to fail.

Question 10

Hybrid search in Vector Search

Accepted Answer

Hybrid search combines vector similarity with keyword matching, which helps when queries contain rare proper nouns, codes, or IDs that pure semantic retrieval misses. Use it when exact term matches matter; pure vector search is better when paraphrase and meaning dominate the query.

Question 11

Chunk size tradeoffs

Accepted Answer

Small chunks give precise retrieval but may fragment context so the model cannot see a complete idea. Large chunks preserve surrounding context but dilute relevance and consume the context window faster. Pick chunk size based on document structure and the kind of answer the user needs, then measure retrieval quality rather than guessing.

Question 12

Chunk overlap purpose

Accepted Answer

Overlap between adjacent chunks prevents a single idea from being split at a boundary, so the model still sees enough context to interpret each chunk. Overlap increases storage and token cost, so use it where boundary splits hurt answer quality, not on every pipeline by default.

Question 13

Embedding model selection

Accepted Answer

The embedding model fixes the dimensionality and semantic space of the index, so the query embedder and the index embedder must match exactly. Switching embedding models forces a full reindex because old vectors and new vectors are not comparable. Choose based on language coverage, dimension, latency, and quality on your own evaluation set.

Question 14

Re-ranking in retrieval

Accepted Answer

Re-ranking takes a larger pool of candidate chunks and scores them again with a more expensive model, pushing the most relevant chunks to the top. It is the standard fix when recall is acceptable but top-k precision is poor. The tradeoff is added latency per query, so apply it only after first-stage retrieval is working.

Question 15

Metadata filters in Vector Search

Accepted Answer

Metadata filters restrict retrieval to rows that match conditions such as source, language, or date, so the model only sees eligible evidence. Use them when the user's question implies a scope, for example 2026 policies only. Without filters, the retriever may return older or out-of-scope chunks that mislead the answer.

Question 16

System prompt vs user prompt

Accepted Answer

The system prompt sets persistent behavior such as role, rules, format, and safety constraints that applies across turns. The user prompt carries the per-request instruction and any retrieved context. Put stable instructions in the system prompt so they are not accidentally overridden by user input or context injection.

Question 17

Few-shot prompting

Accepted Answer

Few-shot examples teach the model the desired output pattern by showing labeled input-output pairs in the prompt. It is the cheapest way to steer format, tone, or extraction behavior without training. The risk is that examples consume the context window and can bias the model toward example-specific patterns, so keep examples representative and minimal.

Question 18

Prompt iteration cycle

Accepted Answer

Iterate prompts against an evaluation set, not single conversations, because a prompt that fixes one case often breaks another. Hold the model and retrieval fixed while you change one prompt variable at a time, then re-measure. Prompts committed without an eval set regress silently in production.

Question 19

Context window limits

Accepted Answer

The context window caps how much text the model can attend to in one call, including system prompt, retrieved chunks, conversation history, and the user query. Overstuffing the window causes truncation, higher cost, and sometimes degraded attention. Retrieve selectively and trim history rather than padding the window with low-value context.

Question 20

Pay-per-token vs Provisioned throughput

Accepted Answer

Pay-per-token is the default Foundation Model API mode and is best for prototyping and low or bursty traffic because you only pay for what you use. Provisioned throughput reserves capacity for predictable latency and higher volume, which is the right choice for production workloads that need performance guarantees. Switching to provisioned is a cost tradeoff, not a quality change.

Question 21

Databricks Foundation Model API

Accepted Answer

The Foundation Model API serves curated open and proprietary base models from Databricks-hosted endpoints with a unified interface. It removes the need to stand up your own inference infrastructure and lets you swap models behind a stable endpoint. You still own prompt engineering, evaluation, and governance; the API only provides model access.

Question 22

External model serving

Accepted Answer

External model serving lets you register and call third-party models such as OpenAI or Anthropic through a Databricks-hosted endpoint. The benefit is unified governance, logging, and AI Gateway controls across providers. The cost is added network hop latency and dependency on the external provider's rate limits and availability.

Question 23

Model selection tradeoffs

Accepted Answer

Larger models generally give better quality but raise latency, cost, and context-window pressure. Pick the smallest model that clears your evaluation threshold, not the largest available. Re-evaluate whenever a new model lands, because the cost-quality frontier moves quickly.

Question 24

Serving endpoint configuration

Accepted Answer

A serving endpoint bundles a model with compute and an API. You configure scale, throughput mode, and environment separately from the model, so the same registered model can be served different ways for dev and production. Misconfigured compute is a common cause of latency regressions that look like model-quality problems.

Question 25

MLflow pyfunc for GenAI apps

Accepted Answer

pyfunc packaging lets you bundle a GenAI application including prompts, retrieval, post-processing, and model into one MLflow model with a consistent predict interface. That makes a RAG app deployable through the same Model Serving endpoints used for classical ML, so governance, monitoring, and CI/CD treat it uniformly.

Question 26

MLflow model registry for GenAI

Accepted Answer

Registering the GenAI model in MLflow gives it a version, stage, and lineage, which are the prerequisites for controlled promotion and rollback. Without registration you cannot safely move from prototype to production, because there is no auditable artifact to promote, compare, or roll back.

Question 27

MLflow ResponsesAgent interface

Accepted Answer

ResponsesAgent standardizes how an agent is exposed so Databricks tooling such as playground, evaluation, and deployment can drive it uniformly. Wrapping a custom agent in ResponsesAgent is what enables downstream product features without forcing you to reimplement them. Skipping the wrapper means losing integration with the platform's agent lifecycle.

Question 28

LLMOps stage separation

Accepted Answer

Separate retrieval, prompt assembly, generation, and post-processing into explicit components so each can be measured and swapped independently. Monolithic GenAI apps are hard to debug because a regression could come from any stage with no clear boundary. Stage separation also enables independent CI/CD for prompts, indexes, and models.

Question 29

Inference tables

Accepted Answer

Inference tables automatically log requests and responses for a served model, giving you a queryable history of production traffic. They are the foundation for post-hoc evaluation, drift detection, and retraining decisions. Without them you have no structured record of what the model actually saw or returned in production.

Question 30

Agent vs chain

Accepted Answer

A chain is a fixed sequence of calls where control flow is known at design time. An agent decides which tool or step to call next based on the model's reasoning over intermediate results. Use a chain when the workflow is deterministic; use an agent when the path depends on the content of the answer.

Question 31

Tool calling pattern

Accepted Answer

Tool calling lets the model emit a structured request to invoke an external function such as a search, a database lookup, or a calculator, and then condition its next answer on the returned result. It is the bridge between the model and live data. The model decides when to call a tool, but you define which tools exist and validate the call schema.

Question 32

Databricks LangChain integration

Accepted Answer

The Databricks LangChain integration exposes Vector Search as a vector store and models as LLM components, so you can compose retrieval, prompts, and tools with standard LangChain primitives. The benefit is portability of chain code; the risk is hiding platform-specific behavior behind abstractions, so you still need to understand the underlying Databricks components.

Question 33

LangGraph for stateful agents

Accepted Answer

LangGraph models an agent as a graph of nodes and edges with explicit state passed between them, which is what you need when an agent loops, branches, or keeps memory across turns. Plain LangChain chains are linear, so reach for LangGraph when control flow is conditional or cyclic. The tradeoff is more code and harder debugging for simpler cases.

Question 34

Persistent agent state

Accepted Answer

Persistent state lets an agent remember intermediate results, conversation history, or tool outputs across calls, which is required for multi-step and multi-turn agents. Without persistence the agent restarts every call and cannot reason over prior steps. Choose storage that matches the state's lifetime: in-memory for a request, Delta or a key-value store for cross-session memory.

Question 35

Agent Bricks

Accepted Answer

Agent Bricks are managed Databricks building blocks that handle common agent infrastructure such as tool wiring, memory, and evaluation hooks so you can assemble agents without writing the plumbing yourself. They reduce boilerplate and standardize integration with the platform, which is why the March 18, 2026 blueprint added deeper coverage of them.

Question 36

Model Context Protocol (MCP)

Accepted Answer

MCP standardizes how agents discover and call tools, resources, and prompts across providers and runtimes. It improves interoperability so the same tool can be reused across agent frameworks instead of being rewritten per integration. It does not replace security controls: you still must govern which tools an agent may call and on what data.

Question 37

Managed MCP endpoints in Databricks

Accepted Answer

Databricks can host a managed MCP endpoint that exposes governed resources, for example a Vector Search index, as a tool an agent can call through the standard protocol. This is preferred over custom connectors because the access path stays inside Databricks governance instead of being a bespoke integration you maintain yourself.

Question 38

Groundedness metric

Accepted Answer

Groundedness measures whether the model's answer is supported by the retrieved evidence, not whether the answer reads well or matches a gold answer. A confident, fluent answer that adds facts not in the sources fails groundedness. It is the metric that catches hallucination in RAG apps most directly.

Question 39

Retrieval relevance

Accepted Answer

Retrieval relevance scores whether the retrieved chunks themselves match the user's question, evaluated before the generation step. It isolates retriever quality from generator quality, which lets you fix retrieval without confusing it with prompt or model issues. Low retrieval relevance means no model can rescue the answer.

Question 40

LLM judge rubrics

Accepted Answer

An LLM judge can scale subjective evaluation, but only with an explicit rubric that tells it what to score and how. Without a rubric the judge drifts and produces noisy grades that correlate with length or tone rather than quality. Always calibrate the judge against human-reviewed examples before trusting it at scale.

Question 41

Offline vs online evaluation

Accepted Answer

Offline evaluation runs against a fixed golden set before launch and tells you whether the app meets a quality bar. Online evaluation observes real traffic after launch and catches drift, edge cases, and operational regressions the golden set missed. You need both: offline is the gate, online is the guardrail.

Question 42

Custom evaluation scorers

Accepted Answer

Custom scorers encode domain-specific pass/fail rules, for example must cite a source or must not mention competitor pricing, that generic metrics cannot capture. Add them when business or compliance constraints are not reflected in standard retrieval or groundedness metrics. The March 18, 2026 blueprint added deeper coverage of custom scorers.

Question 43

Online monitoring signals

Accepted Answer

Track latency, error rate, token usage, and prompt length distribution over live traffic to catch regressions that offline tests cannot see. Spikes in latency or failure rate often surface before users complain. Online monitoring is the only way to detect drift caused by upstream model or data changes outside your release cadence.

Question 44

AI Gateway centralized tracking

Accepted Answer

AI Gateway sits between applications and LLM endpoints to centralize usage logging, policy enforcement, and monitoring across teams and providers. Without it, usage data is scattered across individual apps and there is no single place to enforce rate limits, redaction, or provider failover. It is the right tool when leadership needs cross-team visibility into LLM spend and behavior.

Question 45

AI Gateway rate limits

Accepted Answer

AI Gateway rate limits cap requests or tokens per user, team, or application so one noisy consumer cannot monopolize a shared endpoint. They are a direct control for both spend and throughput, which is the right fix when one team's traffic is driving cost or degrading service for everyone else.

Question 46

Unity Catalog for GenAI governance

Accepted Answer

Unity Catalog centralizes access control, lineage, and auditing for data, models, functions, and vector indexes, so a GenAI app can be governed as one asset graph instead of scattered workspace-level controls. It is the foundation when the app must satisfy enterprise permissions, masking, or audit requirements. Ad hoc workspace controls do not scale across teams.

Question 47

Secrets management for external credentials

Accepted Answer

External API tokens and model-provider keys must live in Databricks secret management, not in notebooks, prompts, source code, or run metadata. Embedding credentials in code or prompts creates avoidable disclosure risk and makes rotation painful. Expose secrets only to the identities and jobs that need them.

Question 48

Content safety guardrails

Accepted Answer

Guardrails check both input and output for unsafe or out-of-policy content such as prompt injection, PII, harmful requests, or banned topics before the request reaches the model or the response reaches the user. They are distinct from access control: a user may be authorized to call the app but still submit unsafe input that must be blocked.

Question 49

Databricks AI Functions

Accepted Answer

AI Functions such as ai_parse_document, ai_classify, and ai_extract run AI tasks directly on data in SQL, notebooks, and pipelines, so row-wise inference at scale does not require a custom chain. They fit batch classification, extraction, and summarization over table data. For interactive multi-turn retrieval or tool use, build a RAG or agent app instead.

Question 50

Structured output for extraction

Accepted Answer

When the task is deterministic field extraction such as invoice number, vendor name, or total, ask the model for a fixed JSON schema rather than free text. Schema-driven output is easier to validate, test, and wire into downstream systems, and explicit return-only-JSON instructions reduce parsing failures from stray prose.

Free Databricks GenAI Associate Exam Flashcards

Filter by Topic

Jump to Card

About These Databricks GenAI Associate Flashcards

Topics Covered

Frequently Asked Questions

Databricks Generative AI Engineer Associate

Explore More Databricks Certifications

Databricks Certified Data Engineer Associate

Databricks Certified Data Analyst Associate

Databricks Certified Data Engineer Professional

Databricks Certified Machine Learning Associate

Databricks Certified Associate Developer for Apache Spark

Databricks Certified Context Engineer Associate

More From This Family